© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83625
    Prev
    Next
    INDEX
    Explanations

    rounding and decimals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gerekir
    -0.82
    进入
    -0.80
     entering
    -0.79
    賓
    -0.77
     juzgar
    -0.77
     especially
    -0.76
     followed
    -0.74
    及
    -0.74
    只要
    -0.72
     aukš
    -0.71
    POSITIVE LOGITS
     nearest
    1.19
     two
    1.14
     deux
    0.96
    Nearest
    0.90
    中最
    0.88
     двох
    0.88
    两位
    0.86
     Nearest
    0.85
    urally
    0.84
    Zwei
    0.84
    Activations Density 0.007%

    No Known Activations